© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6496
    Prev
    Next
    INDEX
    Explanations

    code structure after `)`

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on numeric tokens showing floating‐point values (numbers with decimal points).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mia
    0.84
    }">
    0.84
    lear
    0.81
    Idaho
    0.81
    ANCES
    0.81
    }=\
    0.77
    Capable
    0.77
    mated
    0.76
    }')
    0.74
    Chu
    0.73
    POSITIVE LOGITS
     главным
    0.91
     حص
    0.86
     وک
    0.86
     основе
    0.82
     сентября
    0.79
     dictatorship
    0.79
     ها
    0.79
     собствен
    0.78
     большим
    0.78
     нее
    0.77
    Activations Density 0.000%

    No Known Activations